Select the options for Best Subsets Regression

Stat > Regression > Regression > Best Subsets > Options
Free Predictor(s) In Each Model
By default, Minitab displays the best 1-predictor models, the best 2-predictor models, up to the model that includes all the predictors. If you enter a minimum and maximum number of predictors, for example 5 and 12, Minitab only displays the best 5-predictor, 6-predictor,..., and 12-predictor models.
The total number of predictors included in the model does not include the predictors that you specified in Predictors in all models. For example, if you specified two predictors to include in all models, and set the minimum number of predictors to 5 and the maximum number of predictors to 12, Minitab displays models with 7 – 14 predictors.
Enter the minimum number of free predictors to include in the model.
Enter the maximum number of free predictors to include in the model.
Models of each size to print
Enter a number from 1 to 5. For example, if you choose 3, Minitab displays goodness-of-fit statistics for the 3 models of each size that have the highest R2 values.
Fit intercept

Select Fit intercept to include the intercept (also called the constant) in the regression model. In most cases, you should include the constant in the model.

A possible reason to remove the constant is when you can assume that the response is 0 when the predictor values equal 0. For example, consider a model that predicts calories based on the fat, protein, and carbohydrate contents of a food. When the fat, protein, and carbohydrates are 0, the number of calories will also be 0 (or very close to 0).

When you compare models that do not include the constant, use S instead of the R2 statistics to evaluate the fit of models.

Display of results
The expanded table displays 4 additional statistics:
  • The prediction sum of squares (PRESS)
  • The corrected Akaike's Information Criterion (AICc)
  • The Bayesian Information Criterion (BCC)
  • The condition number
For more information on these statistics, go to Interpret all statistics for Best Subsets Regression.